generate_dummy_testset.py

import PIL.Image
import pandas as pd
import tempfile
from pathlib import Path
import zipfile
import numpy as np

if __name__ == "__main__":
    output_path = "/tmp/data/private_testset.zip"
    metadata = pd.read_csv("metadata-subset.csv")
    print(metadata)

    # create temporary directory
    with tempfile.TemporaryDirectory() as tmpdir:
        tmp_path = Path(tmpdir)
        for row in metadata.itertuples():
            # random dimensions
            x = np.random.randint(100, 300)
            y = np.random.randint(100, 300)
            img = PIL.Image.fromarray(
                np.random.randint(0, 255, (x, y, 3), dtype=np.uint8)
            )
            img.save(tmp_path / row.filename)

        # create a zip file
        Path(output_path).parent.mkdir(parents=True, exist_ok=True)
        with zipfile.ZipFile(output_path, "w") as zip_ref:
            for file in tmp_path.iterdir():
                zip_ref.write(file, f"private_testset/{file.name}")